Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag non-idempotent, open-world, destructive behavior, and the description reinforces this with concrete operational detail the annotations cannot express: cost model (1 credit per document, every call billed even with identical data), return shape (hosted URL, never bytes), and expiry semantics tied to `expiration`. This is exactly the kind of cost/side-effect disclosure that matters for a non-idempotent paid write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, each loading distinct information: billing/side effects first, then the action and scope, then the return value and endpoint. No sentence repeats the schema or the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by explaining the return value (hosted file URL that expires) and its expiry coupling to a parameter. Combined with a fully documented 6-parameter schema and rich annotations, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter is already documented in the schema, including defaults for output_type (jpeg) and output_file behavior. The description only echoes the expiration semantics already in the schema, so the baseline of 3 is appropriate — no meaningful additional parameter guidance is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Generate ONE image (JPEG or PNG) from a template and your JSON data'), including the accepted output formats and that input is JSON data. This cleanly separates it from the sibling craftmypdf_create_pdf family without the agent needing to open either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'WRITE' prefix and the credit/billing note tell the agent this is a mutating, paid operation, which implies when it is appropriate. However, no alternative is named and there is no explicit 'use this instead of craftmypdf_create_pdf when you need an image rather than a PDF' routing, so the selection logic is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.